ML Research Wiki / Benchmarks / Object Detection / PeopleArt

PeopleArt

Object Detection Benchmark

Performance Over Time

📊 Showing 6 results | 📏 Metric: mAP

Top Performing Models

Rank Model Paper mAP Date Code
1 Fast R-CNN Detecting People in Artwork with CNNs 59.00 2016-10-27 📦 BathVisArtData/PeopleArt
2 PVT (Pyramid Vision Transformer; trained on PeopleArt and PopArt) 📚 Poses of People in Art: A Data Set for Human Pose Estimation in Digital Art History 49.70 2023-01-12 -
3 TOOD (Task-aligned One-stage Object Detection; trained on PeopleArt and PoPArt) 📚 Poses of People in Art: A Data Set for Human Pose Estimation in Digital Art History 47.80 2023-01-12 -
4 PVT (Pyramid Vision Transformer) Poses of People in Art: A Data Set for Human Pose Estimation in Digital Art History 46.50 2023-01-12 -
5 TOOD (Task-aligned One-stage Object Detection) Poses of People in Art: A Data Set for Human Pose Estimation in Digital Art History 46.10 2023-01-12 -
6 FasterRCNN (trained on StyleCOCO) Improving Object Detection in Art Images Using Only Style Transfer 36.00 2021-02-12 📦 dkadish/Style-Transfer-for-Object-Detection-in-Art

All Papers (6)

Poses of People in Art: A Data Set for Human Pose Estimation in Digital Art History

2023
PVT (Pyramid Vision Transformer; trained on PeopleArt and PopArt)

Poses of People in Art: A Data Set for Human Pose Estimation in Digital Art History

2023
TOOD (Task-aligned One-stage Object Detection; trained on PeopleArt and PoPArt)